- 25 7月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 22 7月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
* add mask fpn r50 2x & minor fix for MODEL ZOO doc (#2747) * cherry-pick bug fix for release/1.5 * fix mask eval for multi-batch (#2772) * cherry-pick bug fix for release/1.5 * fix faster rcnn use im_shape (#2779) * cherry-pick bug fix for release/1.5 * refine bbox_normalize in infer.py (#2781) * refine bbox_normalize in infer.py * add is_bbox_normalize * rename _forward to build * check callable * cherry-pick bug fix for release/1.5 * Prevent module instance from modifying global config (#2790) some of the global config values are reference type, e.g., objects, lists or dicts, if the created module instances modify those values (see FPN and spatial_scale), global config will reflect these changes, and instances of the same class created later will inherit the changed values * Fix command line parsing for non module options (#2839) * fix save_inference_model cannot find feed vars (#2842) * fix save_inference_model cannot find feed vars * remove comment * fix format * add comment for pruned var * add log for prune * Fix train+eval in PaddleDetection(#2847) * resolve conflict merge error * reset data_feed
-
- 05 7月, 2019 1 次提交
-
-
由 Kaipeng Deng 提交于
-
- 01 7月, 2019 2 次提交
- 28 6月, 2019 1 次提交
-
-
由 qingqing01 提交于
* Rename object_detection to PaddleDetection * Small fix for doc
-
- 27 6月, 2019 4 次提交
-
-
由 qingqing01 提交于
* Add GC in train.py by defalut and change data co dataset in configs * Update docs/INSTALL.md * Enable build_strategy.enable_inplace = True
-
由 Kaipeng Deng 提交于
-
由 Yang Zhang 提交于
* Fix missing `absolute_import` * Fix cycle import * Fix missing export * Remove some extra blank line and whitespaces * Rename `create_feeds` -> `create_feed` * Fix minor issues in tool scripts * Add ipython notebook demo * Tweak visualization bbox label style
-
由 Kaipeng Deng 提交于
* add VOC visualize * fixn ssd_mobilenet_v1_voc.yml * use default label * clean TestFeed dataset config * fix voc default label * fix format * fix as review * revert voc default * use defult label for all * enable batch size != 1
-
- 26 6月, 2019 1 次提交
-
-
由 Yang Zhang 提交于
* Tweak command line scripts enable fine grained control of command flags parsing switch to attribute style of accessing config options * Break down visualization function decouple it from IO operations * Move flag parsing out of `main()` * Fix a bug where `None` is returned instead of `{}` * Rename `save_xxx` to `output_xxx` in command line flags could be confusing since checkpoint is stored in `save_dir` * Support image file extensions in upper case
-
- 25 6月, 2019 1 次提交
-
-
由 Kaipeng Deng 提交于
* refine infer with args * remove samples * fix as review * refine code * refine args * move get_test_images to infer.py * add visualize log * fix images = [] * fix args * refine infer.py * fix yolov3_r34.yml
-
- 24 6月, 2019 2 次提交
-
-
由 Yang Zhang 提交于
-
由 qingqing01 提交于
* Unified object detection framework based on PaddlePaddle. * Include algo: Faster, Mask, FPN, Cascade, RetinaNet, Yolo v3, SSD.
-